Section: New Results

Segmentation multi-vues par coupure de graphes

In this paper, we address the problem of object segmentation in multiple views when two or more viewpoints of the same scene are available. We propose a new approach that propagates segmentation coherence information in space, hence allowing evidence in one image to be shared over the complete set. To this aim the segmentation is cast as a single efficient labeling problem over space and time with graph cuts. In contrast to most existing multi-view segmentation methods that rely on some form of dense reconstruction, ours only requires a sparse 3D sampling to propagate information between viewpoints. The approach is thoroughly evaluated on standard multi-view datasets. The obtained results compete with state of the art methods but they are achieved with significantly fewer viewpoints.

Figure 6. Results of our multi-view segmentation approach over 3 input views, with no user interaction (completely automated). [9]